{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T05:22:52Z","timestamp":1737264172333,"version":"3.33.0"},"reference-count":15,"publisher":"Wiley","issue":"13","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":5923,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp;amp; Computers in Japan"],"published-print":{"date-parts":[[1991,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper proposes a speaker adaptation method for speech recognition based on the discrete hidden Markov models (HMM), especially the fenonic Markov model, which is a framewise model. The method consists largely of two parts\u2014the adaptation of the vector quantization codebook and the adaptation of Markov models. The former employs a method which is based on the difference between the feature parameter distributions of the training speech and the word baseform as the basis for the adaptation, where the two are divided into N segments on the time axis. The latter employs a method based on a linear mapping, which is estimated from the matching between the quantized training speech and the word baseform.<\/jats:p><jats:p>In this study, a recognition experiment was executed using 150 words with high similarities. Using the speech in which all object words are uttered ten times by a male, the codebook and the Markov models are estimated as the basis for the adaptation. Then the adaptation training is executed for seven males and four females by uttering once 25 words in the object vocabulary. The average error rate, i.e., 25.0 and 45.2 percent, respectively, for the males and females, is improved to 4.1 and 7.8 percent. Thus, the usefulness of the proposed method is demonstrated.<\/jats:p>","DOI":"10.1002\/scj.4690221306","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T20:26:20Z","timestamp":1183839980000},"page":"47-58","source":"Crossref","is-referenced-by-count":0,"title":["Speaker adaptation method for fenonic markov model\u2010based speech recognition"],"prefix":"10.1002","volume":"22","author":[{"given":"Masafumi","family":"Nishimura","sequence":"first","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2007,3,21]]},"reference":[{"key":"e_1_2_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"e_1_2_1_3_2","doi-asserted-by":"crossref","unstructured":"L. R.Bahl P. F.Brown P. V.de Souza R. L.Mercer andM. A.Picheny.Acoustic Markov models used in the TANGORA speech recognition system. Proc. ICASSP'88 S11.3 pp.497\u2013500(1988).","DOI":"10.1109\/ICASSP.1988.196628"},{"key":"e_1_2_1_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1984.tb00023.x"},{"issue":"8","key":"e_1_2_1_5_2","first-page":"1041","article-title":"Large vocabulary word recognition using pseudophoneme templates","volume":"65","author":"Sugamura N.","year":"1982","journal-title":"Trans. (D), I.E.I.C.E., Japan"},{"key":"e_1_2_1_6_2","unstructured":"K.NakajimaandS.Takahashi.A method of speaker adaptation for large vocabulary word recognition. Proc. Acoustics 1\u20101\u20106 (Oct.1983)."},{"key":"e_1_2_1_7_2","doi-asserted-by":"crossref","unstructured":"K.Shikano K\u2010F.Lee andR.Reddy.Speaker adaptation through vector quantization. Proc. ICASSP'86 49.5 pp.2643\u20132646(1986).","DOI":"10.1109\/ICASSP.1986.1168676"},{"issue":"8","key":"e_1_2_1_8_2","first-page":"1118","article-title":"Speaker adaptation algorithms based on piecewise moving adaptive segment quantization method","volume":"72","author":"Shiraki Y.","year":"1988","journal-title":"Trans. (D\u2010II), I.E.I.C.E., Japan"},{"key":"e_1_2_1_9_2","doi-asserted-by":"crossref","unstructured":"K.Sugawara M.Nishimura andA.Kuroda.Speaker adaptation for a hidden Markov model. proc. ICASSP'86 49.11 pp.2667\u20132670(1986).","DOI":"10.1109\/ICASSP.1986.1168680"},{"key":"e_1_2_1_10_2","doi-asserted-by":"crossref","unstructured":"R.Schwartz Y.\u2010L.Chow andF.Kubala.Rapid speaker adaptation using a probabilistic spectral mapping. Proc. ICASSP'87 15.3 pp.633\u2013636(1987).","DOI":"10.1109\/ICASSP.1987.1169575"},{"key":"e_1_2_1_11_2","doi-asserted-by":"crossref","unstructured":"M.\u2010W.Feng F.Kubala R.Schwartz andJ.Makhoul.Improved speaker adaptation using text dependent spectral mappings. Proc. ICASSP'88 S3.9 pp.131\u2013134(1988).","DOI":"10.1109\/ICASSP.1988.196529"},{"key":"e_1_2_1_12_2","doi-asserted-by":"crossref","unstructured":"M.NishimuraandK.Sugawara.Speaker adaptation method for HMM\u2010based speech recognition. Proc. ICASSP'88 S5.7 pp.207\u2013210(1988).","DOI":"10.1109\/ICASSP.1988.196550"},{"key":"e_1_2_1_13_2","doi-asserted-by":"crossref","unstructured":"K.Sugawara M.Nishimura K.Toshioka M.Okochi andT.Kaneko.Isolated word recognition using hidden Markov models. Proc. ICASSP'85 1.1 pp.1\u20134(1985).","DOI":"10.1109\/ICASSP.1985.1168452"},{"key":"e_1_2_1_14_2","unstructured":"S.WatanukiandT.Kaneko.Speaker\u2010independent isolated word recognition using N\u2010segment label histogram method. Trans. (D) I.E.I.C.E. Japan J71\u2010D 3 pp.516\u2013522(March1988)."},{"key":"e_1_2_1_15_2","doi-asserted-by":"crossref","unstructured":"M.NishimuraandK.Toshioka.HMM\u2010based speech recognition using multidimensional multilabeling. Proc. ICASSP'87 27.11 pp.1163\u20131166(1987).","DOI":"10.1109\/ICASSP.1987.1169883"},{"key":"e_1_2_1_16_2","doi-asserted-by":"crossref","unstructured":"L. R.Baul R.Bakis P. V.de Souza andR. L.Mercer.Obtaining candidate words by polling in a large vocabulary speech recognition system. Proc. ICASSP'88 S11.1 pp.489\u2013492(1988).","DOI":"10.1109\/ICASSP.1988.196626"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690221306","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690221306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T17:24:28Z","timestamp":1737221068000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690221306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":15,"journal-issue":{"issue":"13","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690221306"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690221306","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"type":"print","value":"0882-1666"},{"type":"electronic","value":"1520-684X"}],"subject":[],"published":{"date-parts":[[1991,1]]}}}